← Back to community benchmarks
Huihui-Qwen3.5-27B-abliterated-8bit
Performance
1k
tokens
122.9
PP tok/s
8.5
TG tok/s
8334
TTFT (ms)
29.1
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 122.9 | 8.5 | 29.1 GB | current |
| 4k | 120.6 | 8.1 | 29.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 8.5 | 1.00× |
| 2× | 16.5 | 1.94× |
| 4× | 22.1 | 2.60× |